-USING: unicode.case tools.test namespaces ;
+! Copyright (C) 2008, 2009 Daniel Ehrenberg.
+! See http://factorcode.org/license.txt for BSD license.
+USING: unicode.case unicode.case.private tools.test namespaces strings unicode.normalize ;
+IN: unicode.case.tests
\ >upper must-infer
\ >lower must-infer
[ "\u0003C3a\u0003C2 \u0003C3\u0003C2 \u0003C3a\u0003C2" ] [ "\u0003A3A\u0003A3 \u0003A3\u0003A3 \u0003A3A\u0003A3" >lower ] unit-test
[ t ] [ "hello how are you?" lower? ] unit-test
[
+ [ f ] [ i-dot? ] unit-test
+ [ f ] [ lt? ] unit-test
"tr" locale set
+ [ t ] [ i-dot? ] unit-test
+ [ f ] [ lt? ] unit-test
[ "i\u000131i \u000131jj" ] [ "i\u000131I\u000307 IJj" >lower ] unit-test
[ "I\u000307\u000131i Ijj" ] [ "i\u000131I\u000307 IJj" >title ] unit-test
[ "I\u000307II\u000307 IJJ" ] [ "i\u000131I\u000307 IJj" >upper ] unit-test
"lt" locale set
- ! Lithuanian casing tests
+ [ f ] [ i-dot? ] unit-test
+ [ t ] [ lt? ] unit-test
+ [ "i\u000307\u000300" ] [ HEX: CC 1string nfd >lower ] unit-test
+ [ "\u00012f\u000307" ] [ HEX: 12E 1string nfd >lower nfc ] unit-test
+ [ "I\u000300" ] [ "i\u000307\u000300" >upper ] unit-test
+! [ "I\u000300" ] [ "i\u000307\u000300" >title ] unit-test
] with-scope
[ t ] [ "asdf" lower? ] unit-test
-! Copyright (C) 2008 Daniel Ehrenberg.
+! Copyright (C) 2008, 2009 Daniel Ehrenberg.
! See http://factorcode.org/license.txt for BSD license.
USING: unicode.data sequences namespaces
sbufs make unicode.syntax unicode.normalize math hints
-unicode.categories combinators unicode.syntax assocs
+unicode.categories combinators unicode.syntax assocs combinators.short-circuit
strings splitting kernel accessors unicode.breaks fry locals ;
QUALIFIED: ascii
IN: unicode.case
: i-dot? ( -- ? )
locale get { "tr" "az" } member? ;
+: lt? ( -- ? )
+ locale get "lt" = ;
+
: lithuanian? ( -- ? ) locale get "lt" = ;
: dot-over ( -- ch ) HEX: 307 ;
: mark-above? ( ch -- ? )
combining-class 230 = ;
-: with-rest ( seq quot: ( seq -- seq ) -- seq )
- [ unclip ] dip swap slip prefix ; inline
+:: with-rest ( seq quot: ( seq -- seq ) -- seq )
+ seq unclip quot dip prefix ; inline
: add-dots ( seq -- seq )
- [ [ "" ] [
- dup first mark-above?
- [ CHAR: combining-dot-above prefix ] when
+ [ [ { } ] [
+ [
+ dup first
+ { [ mark-above? ] [ CHAR: combining-ogonek = ] } 1||
+ [ CHAR: combining-dot-above prefix ] when
+ ] map
] if-empty ] with-rest ; inline
: lithuanian>lower ( string -- lower )
- "i" split add-dots "i" join
- "j" split add-dots "i" join ; inline
+ "I" split add-dots "I" join
+ "J" split add-dots "J" join ; inline
: turk>upper ( string -- upper-i )
"i" "I\u000307" replace ; inline
PRIVATE>
: >lower ( string -- lower )
- i-dot? [ turk>lower ] when final-sigma
+ i-dot? [ turk>lower ] when
+ lt? [ lithuanian>lower ] when
+ final-sigma
[ lower>> ] [ ch>lower ] map-case ;
HINTS: >lower string ;
: >upper ( string -- upper )
i-dot? [ turk>upper ] when
+ lt? [ lithuanian>upper ] when
[ upper>> ] [ ch>upper ] map-case ;
HINTS: >upper string ;
: (>title) ( string -- title )
i-dot? [ turk>upper ] when
+ lt? [ lithuanian>upper ] when
[ title>> ] [ ch>title ] map-case ; inline
: title-word ( string -- title )